[SIGGRAPH 2026 / TOG] Official code of the paper "UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors".

Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds. 面向游戏与虚拟世界的AI原生渲染引擎

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

[NeurIPS 2025] Video World Models with Long-term Spatial Memory

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Helios: Real Real-Time Long Video Generation Model

Project Lyra: Open Generative 3D World Models

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

Project AirSim is Microsoft's evolution of AirSim, an advanced simulation platform for building, training, and testing autonomous systems in high-fidelity virtual environments

Open-source simulator for autonomous driving research.

[CVPR 2026] EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

C2R: Coarse-to-Real

Advancing Open-source World Models

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

[ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

[CVPR 2025] Code for Segment Any Motion in Videos

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

[SIGGRAPH 2025] Official Repo for Paper - GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering

Code for "CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects", NeurIPS 2025

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

A high-throughput and memory-efficient inference and serving engine for LLMs

Wan: Open and Advanced Large-Scale Video Generative Models